Data-efficient flood depth prediction through domain-aware coreset selection and tabular foundation models

Researchers have developed a data-efficient flood depth prediction method that uses domain-aware coreset selection and tabular foundation models, achieving near-real-time accuracy with only 0.7% of the training data typically required. The model, tested across nine Houston-area watersheds, reached a mean R² of 0.663—within 98.5% of the supervised reference—and transferred to new watersheds without retraining. This approach enables fast, transferable flood predictions that outperform supervised baselines on out-of-distribution storms, reducing the need for per-watershed training data.

arXiv:2606.05265v1 Announce Type: new Abstract: Near-real-time flood depth prediction demands surrogate models that are accurate, fast, and transferable across watersheds. Supervised surrogates can match physics-based simulators in accuracy but need millions of training rows per watershed and cannot extrapolate beyond their original mesh. We propose a domain-aware coreset construction pipeline that conditions a tabular foundation model at inference time. The pipeline stratifies storms by return period and most-affected watershed, then samples hexagons with a target-aware spatial selector. With 0.7% of the per-watershed training pool, the model attains a mean $R^2$ of 0.663 across nine Houston-area watersheds, within 98.5% of the supervised reference $R^2$ = 0.673 . It transfers to held-out watersheds without task-specific retraining, staying ahead of a coreset-trained supervised baseline. On real storms it exceeds the supervised reference on a far out-of-distribution case and trails it on a mostly in-distribution one. Domain-aware coreset construction lets tabular foundation models deliver data-efficient, watershed-transferable flood predictions without per-watershed training.